© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17283
    Prev
    Next
    INDEX
    Explanations

    words related to receiving support and backing for a project or cause

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Digest
    -0.68
     Kills
    -0.66
    itability
    -0.63
    entary
    -0.62
    Enlarge
    -0.61
    ENSE
    -0.61
     Prohibition
    -0.60
    ute
    -0.60
    shift
    -0.58
    onica
    -0.58
    POSITIVE LOGITS
     gotten
    1.49
    been
    1.43
     been
    1.35
     gone
    1.31
     risen
    1.27
     begun
    1.26
     eaten
    1.24
     undergone
    1.19
     taken
    1.19
     fallen
    1.16
    Activations Density 0.216%

    No Known Activations